{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27647437", "kind": "science-record", "revision": 6, "content_hash": "sha256:402e7f8af7a890f3a63ad3e03826f2632c0129c856c9ce4da3f7fc822f247a21", "created_at": "2026-11-01T15:40:20Z", "updated_at": "2026-11-01T21:20:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A long non-coding RNA signature to improve prognosis prediction of gastric cancer.", "doi": "10.1186/s12943-016-0544-0", "pmid": "27647437", "authors": ["Xiaoqiang Zhu", "Xianglong Tian", "Chenyang Yu", "Chaoqin Shen", "Tingting Yan", "Jie Hong", "Zheng Wang", "Jing-Yuan Fang", "Haoyan Chen"], "journal": "Molecular cancer", "year": 2016, "abstract": "BACKGROUND: Increasing evidence suggests long non-coding RNAs (lncRNAs) are frequently aberrantly expressed in cancers, however, few related lncRNA signatures have been established for prediction of cancer prognosis. We aimed at developing alncRNA signature to improve prognosis prediction of gastric cancer (GC).\nMETHODS: Using a lncRNA-mining approach, we performed lncRNA expression profiling in large GC cohorts from Gene Expression Ominus (GEO), including GSE62254 data set (N = 300) and GSE15459 data set (N = 192). We established a set of 24-lncRNAs that were significantly associated with the disease free survival (DFS) in the test series.\nRESULTS: Based on this 24-lncRNA signature, the test series patients could be classified into high-risk or low-risk subgroup with significantly different DFS (HR = 1.19, 95 % CI = 1.13-1.25, P < 0.0001). The prognostic value of this 24-lncRNA signature was confirmed in the internal validation series and another external validation series, respectively. Further analysis revealed that the prognostic value of this signature was independent of lymph node ratio (LNR) and postoperative chemotherapy. Gene set enrichment analysis (GSEA) indicated that high risk score group was associated with several cancer recurrence and metastasis associated pathways.\nCONCLUSIONS: The identification of the prognostic lncRNAs indicates the potential roles of lncRNAs in GC biogenesis. Our results may provide an efficient classification tool for clinical prognosis evaluation of GC.", "claims": [{"id": "claim-method", "statement": "Those 63 genes were further analyzed by random survival forest-variable hunting (RSF-VH) algorithm [36].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27647437", "locator": "sections[9] \"Identification of prognostic lncRNA genes from the test series\" paragraph 2", "quote": "Those 63 genes were further analyzed by random survival forest-variable hunting (RSF-VH) algorithm [36]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The gene expression data in this study can be found online at the Gene Expression Omnibus under accession numbers GSE62254 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254) and GSE15459 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27647437", "locator": "sections[26] \"ack\" paragraph 1", "quote": "The gene expression data in this study can be found online at the Gene Expression Omnibus under accession numbers GSE62254 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254) and GSE15459 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A 24-lncRNA signature developed using sample splitting, random survival forests-variable hunting, and Cox regression from GEO microarray cohorts stratified gastric cancer patients into high- and low-risk groups with significantly different disease-free survival (HR = 1.19, 95% CI = 1.13–1.25, P < 0.0001).", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "Based on this 24-lncRNA signature, the test series patients could be classified into high-risk or low-risk subgroup with significantly different DFS (HR = 1.19, 95 % CI = 1.13–1.25, P < 0.0001)."}, "evidence": [{"asset": "source:pmid:27647437", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Based on this 24-lncRNA signature, the test series patients could be classified into high-risk or low-risk subgroup with significantly different DFS (HR = 1.19, 95 % CI = 1.13–1.25, P < 0.0001)."}, {"asset": "source:pmid:27647437", "locator": "sections[1] \"Background\" paragraph 4", "quote": "By using the sample-splitting method, random survival forests-variable hunting (RSF-VH) algorithm and Cox regression analysis, we identified a prognostic, 24-lncRNA signature from the GSE62254 test series patients, and validated it in the GSE62254 validation series and another independent GEO cohort (GSE15459)."}, {"asset": "source:pmid:27647437", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Using a lncRNA-mining approach, we performed lncRNA expression profiling in large GC cohorts from Gene Expression Ominus (GEO), including GSE62254 data set (N = 300) and GSE15459 data set (N = 192)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A 24-lncRNA signature developed using sample splitting, random survival forests-variable hunting, and Cox regression from GEO microarray cohorts stratified gastric cancer patients into high- and low-risk groups with significantly different disease-free survival (HR = 1.19, 95% CI = 1.13–1.25, P < 0.0001).", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:27647437"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE15459"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE15459"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27647437", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12943-016-0544-0", "sha256": "sha256:9d094c6cc0b0c034be2762cd0dabfde64b916b58ba4669d0172119e54211ab38", "bytes": 49619, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12943-016-0544-0", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5029104", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15459", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15459", "version": null, "note": "The gene expression data in this study can be found online at the Gene Expression Omnibus under accession numbers GSE62254 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254) and GSE15459 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression data in this study can be found online at the Gene Expression Omnibus under accession numbers GSE62254 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254) and GSE15459 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM387788", "GSM387789", "GSM387790", "GSM387791", "GSM387792", "GSM387793", "GSM387794", "GSM387795", "GSM387796", "GSM387797", "GSM387798", "GSM387799", "GSM387800", "GSM387801", "GSM387802", "GSM387803", "GSM387804", "GSM387805", "GSM387806", "GSM387807", "GSM387808", "GSM387809", "GSM387810", "GSM387811", "GSM387812", "GSM387813", "GSM387814", "GSM387815", "GSM387816", "GSM387817", "GSM387818", "GSM387819", "GSM387820", "GSM387821", "GSM387822", "GSM387823", "GSM387824", "GSM387825", "GSM387826", "GSM387827", "GSM387828", "GSM387829", "GSM387830", "GSM387831", "GSM387832", "GSM387833", "GSM387834", "GSM387835", "GSM387836", "GSM387837", "GSM387838", "GSM387839", "GSM387840", "GSM387841", "GSM387842", "GSM387843", "GSM387844", "GSM387845", "GSM387846", "GSM387847", "GSM387848", "GSM387849", "GSM387850", "GSM387851", "GSM387852", "GSM387853", "GSM387854", "GSM387855", "GSM387856", "GSM387857", "GSM387858", "GSM387859", "GSM387860", "GSM387861", "GSM387862", "GSM387863", "GSM387864", "GSM387865", "GSM387866", "GSM387867", "GSM387868", "GSM387869", "GSM387870", "GSM387871", "GSM387872", "GSM387873", "GSM387874", "GSM387875", "GSM387876", "GSM387877", "GSM387878", "GSM387879", "GSM387880", "GSM387881", "GSM387882", "GSM387883", "GSM387884", "GSM387885", "GSM387886", "GSM387887", "GSM387888", "GSM387889", "GSM387890", "GSM387891", "GSM387892", "GSM387893", "GSM387894", "GSM387895", "GSM387896", "GSM387897", "GSM387898", "GSM387899", "GSM387900", "GSM387901", "GSM387902", "GSM387903", "GSM387904", "GSM387905", "GSM387906", "GSM387907", "GSM387908", "GSM387909", "GSM387910", "GSM387911", "GSM387912", "GSM387913", "GSM387914", "GSM387915", "GSM387916", "GSM387917", "GSM387918", "GSM387919", "GSM387920", "GSM387921", "GSM387922", "GSM387923", "GSM387924", "GSM387925", "GSM387926", "GSM387927", "GSM387928", "GSM387929", "GSM387930", "GSM387931", "GSM387932", "GSM387933", "GSM387934", "GSM387935", "GSM387936", "GSM387937", "GSM387938", "GSM387939", "GSM387940", "GSM387941", "GSM387942", "GSM387943", "GSM387944", "GSM387945", "GSM387946", "GSM387947", "GSM387948", "GSM387949", "GSM387950", "GSM387951", "GSM387952", "GSM387953", "GSM387954", "GSM387955", "GSM387956", "GSM387957", "GSM387958", "GSM387959", "GSM387960", "GSM387961", "GSM387962", "GSM387963", "GSM387964", "GSM387965", "GSM387966", "GSM387967", "GSM387968", "GSM387969", "GSM387970", "GSM387971", "GSM387972", "GSM387973", "GSM387974", "GSM387975", "GSM387976", "GSM387977", "GSM387978", "GSM387979", "GSM387980", "GSM387981", "GSM387982", "GSM387983", "GSM387984", "GSM387985", "GSM387986", "GSM387987"], "sample_count": 200, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gastric Cancer Project '08 (Singapore Patient Cohort)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE62254", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62254", "version": null, "note": "The gene expression data in this study can be found online at the Gene Expression Omnibus under accession numbers GSE62254 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254) and GSE15459 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression data in this study can be found online at the Gene Expression Omnibus under accession numbers GSE62254 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254) and GSE15459 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1523727", "GSM1523728", "GSM1523729", "GSM1523744", "GSM1523745", "GSM1523746", "GSM1523747", "GSM1523748", "GSM1523765", "GSM1523768", "GSM1523769", "GSM1523770", "GSM1523771", "GSM1523772", "GSM1523773", "GSM1523774", "GSM1523775", "GSM1523776", "GSM1523777", "GSM1523778", "GSM1523779", "GSM1523780", "GSM1523781", "GSM1523782", "GSM1523783", "GSM1523784", "GSM1523785", "GSM1523786", "GSM1523787", "GSM1523788", "GSM1523789", "GSM1523790", "GSM1523791", "GSM1523792", "GSM1523793", "GSM1523794", "GSM1523795", "GSM1523796", "GSM1523797", "GSM1523798", "GSM1523799", "GSM1523800", "GSM1523801", "GSM1523802", "GSM1523803", "GSM1523804", "GSM1523805", "GSM1523806", "GSM1523807", "GSM1523808", "GSM1523809", "GSM1523810", "GSM1523811", "GSM1523812", "GSM1523813", "GSM1523814", "GSM1523815", "GSM1523816", "GSM1523817", "GSM1523818", "GSM1523819", "GSM1523820", "GSM1523821", "GSM1523822", "GSM1523823", "GSM1523824", "GSM1523825", "GSM1523826", "GSM1523827", "GSM1523828", "GSM1523829", "GSM1523830", "GSM1523831", "GSM1523832", "GSM1523833", "GSM1523834", "GSM1523835", "GSM1523836", "GSM1523837", "GSM1523838", "GSM1523839", "GSM1523840", "GSM1523841", "GSM1523842", "GSM1523843", "GSM1523844", "GSM1523845", "GSM1523846", "GSM1523847", "GSM1523848", "GSM1523849", "GSM1523850", "GSM1523851", "GSM1523852", "GSM1523853", "GSM1523854", "GSM1523855", "GSM1523856", "GSM1523857", "GSM1523858", "GSM1523859", "GSM1523860", "GSM1523861", "GSM1523862", "GSM1523863", "GSM1523864", "GSM1523865", "GSM1523866", "GSM1523867", "GSM1523868", "GSM1523869", "GSM1523870", "GSM1523871", "GSM1523872", "GSM1523873", "GSM1523874", "GSM1523875", "GSM1523876", "GSM1523877", "GSM1523878", "GSM1523879", "GSM1523880", "GSM1523881", "GSM1523882", "GSM1523883", "GSM1523884", "GSM1523885", "GSM1523886", "GSM1523887", "GSM1523888", "GSM1523889", "GSM1523890", "GSM1523891", "GSM1523892", "GSM1523893", "GSM1523894", "GSM1523895", "GSM1523896", "GSM1523897", "GSM1523898", "GSM1523899", "GSM1523901", "GSM1523903", "GSM1523904", "GSM1523905", "GSM1523906", "GSM1523908", "GSM1523909", "GSM1523910", "GSM1523911", "GSM1523918", "GSM1523919", "GSM1523920", "GSM1523921", "GSM1523922", "GSM1523923", "GSM1523924", "GSM1523925", "GSM1523926", "GSM1523927", "GSM1523928", "GSM1523929", "GSM1523930", "GSM1523931", "GSM1523932", "GSM1523933", "GSM1523934", "GSM1523935", "GSM1523936", "GSM1523937", "GSM1523938", "GSM1523939", "GSM1523940", "GSM1523941", "GSM1523942", "GSM1523943", "GSM1523944", "GSM1523945", "GSM1523946", "GSM1523947", "GSM1523948", "GSM1523949", "GSM1523950", "GSM1523951", "GSM1523952", "GSM1523953", "GSM1523954", "GSM1523955", "GSM1523956", "GSM1523957", "GSM1523958", "GSM1523959", "GSM1523960", "GSM1523961", "GSM1523962", "GSM1523963", "GSM1523964", "GSM1523965", "GSM1523966", "GSM1523967", "GSM1523968", "GSM1523969", "GSM1523970", "GSM1523971", "GSM1523972", "GSM1523973", "GSM1523974", "GSM1523975", "GSM1523976", "GSM1523977", "GSM1523978", "GSM1523979", "GSM1523980", "GSM1523981", "GSM1523982", "GSM1523983", "GSM1523984", "GSM1523985", "GSM1523986", "GSM1523987", "GSM1523988", "GSM1523989", "GSM1523990", "GSM1523991", "GSM1523992", "GSM1523993", "GSM1523994", "GSM1523995", "GSM1523996", "GSM1523997", "GSM1523998", "GSM1523999", "GSM1524000", "GSM1524001", "GSM1524002", "GSM1524003", "GSM1524004", "GSM1524005", "GSM1524006", "GSM1524007", "GSM1524008", "GSM1524009", "GSM1524010", "GSM1524011", "GSM1524012", "GSM1524013", "GSM1524014", "GSM1524015", "GSM1524016", "GSM1524017", "GSM1524018", "GSM1524019", "GSM1524020", "GSM1524021", "GSM1524022", "GSM1524023", "GSM1524024", "GSM1524025", "GSM1524026", "GSM1524027", "GSM1524028", "GSM1524029", "GSM1524030", "GSM1524031", "GSM1524032", "GSM1524033", "GSM1524034", "GSM1524035", "GSM1524036", "GSM1524037", "GSM1524038", "GSM1524039", "GSM1524040", "GSM1524041", "GSM1524042", "GSM1524043", "GSM1524044", "GSM1524045", "GSM1524046", "GSM1524047", "GSM1524048", "GSM1524049", "GSM1524050", "GSM1524051", "GSM1524052", "GSM1524053", "GSM1524054", "GSM1524055", "GSM1524056", "GSM1524057", "GSM1524058", "GSM1524059", "GSM1524060", "GSM1524061", "GSM1524062", "GSM1524068", "GSM1524069", "GSM1524070", "GSM1524071", "GSM1524072"], "sample_count": 300, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Molecular analysis of gastric cancer identifies discrete subtypes associated with distinct clinical characteristics and survival outcomes: the ACRG (Asian Cancer Research Group) study [gastric tumors]", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:27647437:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c023961bc941229aa7d481fa0cbcccc2db62f7ea759d755a8f63135682e0cabf", "bytes": 2888, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab1", "version": null, "note": "LncRNAs significantly associated with the disease free survival in the test series patients (N = 180)", "structure": {"pmcid": "PMC5029104", "section_index": 9, "section_title": "Identification of prognostic lncRNA genes from the test series", "row_count": 25, "column_count": 8}, "table": {"label": "Table 1", "caption": "LncRNAs significantly associated with the disease free survival in the test series patients (N = 180)", "rows": [["Probe", "Gene symbol", "Permutation P valuea,b", "Hazard ratioa", "Coefficienta", "VI", "Associated diseases", "Description"], ["233512_at", "AF035291", "0.0017", "8.325", "2.11846", "0.012", "NR", "hypothetical LOC100287216"], ["1568854_at", "AI028608", "0.0084", "6.839", "1.92247", "−0.002", "NR", "non-protein coding RNA 240"], ["229280_s_at", "AK026189", "6.00E-04", "4.633", "1.53266", "0.006", "Melanoma and basal cell carcinoma", "promotes metastasis and recurrence of melanoma"], ["1559412_at", "H04858", "8.00E-04", "4.030", "1.3926", "0.002", "Acute megakaryoblastic leukemia", "Maintenance of leukemic growth"], ["1559965_at", "BC037827", "0.0018", "3.587", "1.27718", "0.053", "NR", "hypothetical LOC100192378"], ["1557338_x_at", "BC038210", "0.0108", "3.326", "1.20171", "0.017", "NR", "NR"], ["230589_at", "AI916498", "0.0034", "2.844", "1.04591", "−0.006", "Gastric cancer", "Sensitivity of iodine-125 particle irradiation and regulation of NF-KB signaling pathway"], ["239466_at", "AA463827", "0.0013", "2.799", "1.0294", "0.026", "NR", "hypothetical LOC344595"], ["230251_at", "AA041523", "0.0014", "2.521", "0.92436", "0.038", "Non-small cell lung cancer", "Associated with loss function of LKB1 gene"], ["225029_at", "BE621082", "0.0016", "2.249", "0.81047", "0.007", "Systemic lupus erythematosus", "A novel susceptibility locus on Xp11.21"], ["1564139_at", "AK056852", "0.0016", "1.923", "0.65369", "0.004", "NR", "hypothetical LOC144571"], ["229014_at", "AW206234", "0.0021", "1.718", "0.54056", "0.002", "NR", "hypothetical LOC441094"], ["1558828_s_at", "AL703532", "0.0032", "1.325", "0.2811", "0.005", "Heart failure associated diseases", "Regulation of cardiac cell differentiation and homeostasis"], ["235759_at", "AI095542", "0.0034", "1.282", "0.24825", "−0.004", "NR", "NR"], ["213972_at", "AI080288", "0.0036", "0.155", "−1.86125", "−0.007", "NR", "NR"], ["1554880_at", "BC021187", "0.0024", "0.106", "−2.24862", "−0.002", "Gastric cancer", "Protective roles for gastric cancer"], ["235824_at", "BF238392", "0.0019", "0.073", "−2.61423", "0.012", "NR", "NR"], ["232191_at", "BC005107", "0.0076", "0.070", "−2.65478", "0.002", "NR", "chromosome 21 open reading frame 105"], ["1563296_at", "BC039674", "0.0022", "0.068", "−2.69258", "0.000", "NR", "NR"], ["239617_at", "AI056187", "9.00E-04", "0.061", "−2.79863", "−0.001", "Gastric cancer", "spans the promoter and untranslated regions\\of the ghrelin gene"], ["243975_at", "T79746", "0.0031", "0.058", "−2.85076", "0.003", "NR", "NR"], ["1558666_at", "H11436", "3.00E-04", "0.055", "−2.89127", "−0.007", "NR", "NR"], ["237471_at", "BF511694", "0.0034", "0.041", "−3.19733", "0.003", "NR", "hypothetical LOC154822"], ["1562683_a_at", "BC035722", "0.0023", "0.033", "−3.40924", "0.001", "NR", "hypothetical LOC285547"]], "row_count": 25, "column_count": 8, "numeric_cells": 155, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:27647437:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:16fc4747ecc3967e4fe45454c8199ee6ac6af6d1db81a395e7a0b447b2c57a23", "bytes": 1074, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab2", "version": null, "note": "Multivariable Cox regression analysis of the 24-lncRNA risk score, LNR and postoperative chemotherapy in GSE62254 series", "structure": {"pmcid": "PMC5029104", "section_index": 13, "section_title": "Prognostic value of the 24-lncRNA signature is independent of LNR", "row_count": 17, "column_count": 4}, "table": {"label": "Table 2", "caption": "Multivariable Cox regression analysis of the 24-lncRNA risk score, LNR and postoperative chemotherapy in GSE62254 series", "rows": [["Variables", "HR", "95 % CI of HR", "P value"], ["24-lncRNA risk score (N = 300)", "1.16", "1.10 –1.21", "<0.0001"], ["LNR", "4.33", "1.34 –13.93", "0.014"], ["Age", "1.03", "1.00 –1.05", "0.032"], ["Gender", "1.10", "0.65 –1.84", "0.732"], ["TNM stage I", "1.00(referent)", "", ""], ["TNM stage II", "1.08", "0.23 –5.08", "0.919"], ["TNM stage III", "2.09", "0.47 –9.24", "0.330"], ["TNM stage IV", "3.89", "0.82 –18.44", "0.087"], ["24-lncRNA risk score (N = 299)", "1.14", "1.09 –1.19", "< 0.0001"], ["Postoperative chemotherapy", "0.36", "0.18 –0.73", "0.004"], ["Age", "1.01", "0.99 –1.03", "0.324"], ["Gender", "1.04", "0.62 –1.75", "0.897"], ["TNM stage I", "1.00(referent)", "", ""], ["TNM stage II", "1.47", "0.31 –6.85", "0.626"], ["TNM stage III", "4.00", "0.93 –17.15", "0.062"], ["TNM stage IV", "8.50", "2.00 –36.20", "0.004"]], "row_count": 17, "column_count": 4, "numeric_cells": 47, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab2"}}], "gaps": ["asset:data:geo:GSE15459 not downloaded", "asset:data:geo:GSE15459 licence not read", "asset:data:geo:GSE62254 not downloaded", "asset:data:geo:GSE62254 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": null, "specific": null, "label": "Random survival forest-variable hunting (RSF-VH) algorithm", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Those 63 genes were further analyzed by random survival forest-variable hunting (RSF-VH) algorithm [36]."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-hazard-ratio", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 1.19, "unit": "hazard ratio", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-p-value", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 0.0001, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE62254", "GSE15459"], "resolved_accessions": ["GSE62254", "GSE15459"], "statements": ["The gene expression data in this study can be found online at the Gene Expression Omnibus under accession numbers GSE62254 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE62254) and GSE15459 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE15459)."], "basis": "The paper names GSE62254, GSE15459 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:27647437", "data:geo:GSE15459", "asset:table:pmid:27647437:1", "asset:table:pmid:27647437:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15459"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:20Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 98775, "completion_tokens": 3208, "cached_tokens": 1560}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:27647437", "type": "paper", "label": "pmid:27647437"}, {"id": "source:pmid:27647437", "type": "manuscript", "label": "PMID 27647437 full text"}, {"id": "data:geo:GSE15459", "type": "dataset", "label": "GEO GSE15459"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27647437", "type": "paper", "label": "pmid:27647437"}, {"id": "source:pmid:27647437", "type": "manuscript", "label": "PMID 27647437 full text"}, {"id": "data:geo:GSE15459", "type": "dataset", "label": "GEO GSE15459"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27647437", "type": "extraction", "used": ["source:pmid:27647437"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15459", "type": "accession_resolution", "used": ["data:geo:GSE15459"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:27647437", "parent_hash": "sha256:7a4a46cef44c74f1ae9d80e9a53cca5c4c69aa95299ec34b4978e4e550829f9c", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE15459 licence not read", "asset:data:geo:GSE15459 not downloaded", "asset:data:geo:GSE62254 licence not read", "asset:data:geo:GSE62254 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Methods Microarray data processing and lncRNA profile mining Th", "qin Zhang et al [32]. Briefly, we mapped the Affymetrix HG-U133 Plus 2.0 probe set IDs to the NetAff", "otated lncRNA transcripts with corresponding Affymetrix probe IDs were generated. The 24-lncRNA sign"], "order_basis": "paper_text_order:1601", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:48:51+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}